Hugging Face's logo

Spaces:
shamiur
/
sunnyware
Running on Zero

App Files Community
1
sunnyware / src

Commit History

Yesterday

  1. Part 697b: Log Jarvis-routed tool calls for live analytics counts

    shamiur
    1d4530a

  2. Part 697: Clean up stale 'no calls recorded' reason for live tools

    shamiur
    f968e0f

  3. Part 697: Merge live tool call counts from analytics_store into /api/tools/health

    shamiur
    6c3de8d

  4. Part 694 fix: Correct date_calc test case and skip memory_search (DB required)

    shamiur
    940b477

  5. Part 694 fix: Rename tools-test endpoint to avoid route collision

    shamiur
    6c100e0

  6. Part 693-A: Expand tools dropdown with all 83 tools, categories, and search

    shamiur
    48c559d

  7. Part 690: Fix static mount path to repo root static/ directory

    shamiur
    3ed7724

  8. Part 689: Serve highlight.js locally (stub) to silence CDN warnings

    shamiur
    11405a5

  9. Part 689: Whitelist /api/sessions, /api/roles from 2FA

    shamiur
    d2f4ad0

  10. Part 685: Add /share/{chat_id} endpoint for public link sharing

    shamiur
    fb2e895

  11. Part 673: Server-side chat persistence for Incognito support

    shamiur
    d0b0377

  12. Part 671: Local fallback, API key rotation, chat export/regenerate in dropdown, and admin alerts

    shamiur
    bf87eea

  13. Part 670: Markdown tables, routing strategy dropdown, and API key management

    shamiur
    db6a540

  14. Part 669: Lower auto-disable threshold from 50% to 25%

    shamiur
    38207e2

  15. Part 666 fix: auto-recovery loop starts in a thread when no event loop

    shamiur
    a412d48

  16. Part 668 fix: add cost_tier to providers without stats (fixes local showing Paid)

    shamiur
    7a3713a

  17. Part 668: Cost tracking, usage bars, and chat copy buttons

    shamiur
    fb4bd1c

  18. Part 666: Add auto-recovery background loop and toast notifications

    shamiur
    2c657ee

  19. Part 665: Add Force Recover button and logic

    shamiur
    51424ee

  20. Part 663 fix: add auto_disabled field to providers without stats

    shamiur
    65af8a1

  21. Part 663: Finalize auto-disable logic — remove stale override references

    shamiur
    6b11020

  22. Part 663: Remove 1-hour override from Reset so auto-disable can trigger

    shamiur
    e8c5f02

  23. Part 663: Lower auto-disable threshold to >=3 calls for faster triggering

    shamiur
    b103f15

  24. Part 663 fix: write auto_disabled flag and reset override to llm_dashboard.py

    shamiur
    2091b69

  25. Part 662: Add Tokens by Model table; replace SmolLM download with GGUF cleanup; remove stale env override

    shamiur
    5ca3a00

  26. Part 659: Usage Analytics dashboard — tokens/cost per provider, user, day

    shamiur
    d193369

  27. Part 658: Test results now logged to health stats; 402/credits get 3600s cooldown

    shamiur
    15fb7b1

  28. Part 657: Test endpoint marks cooldowns on failure so quota errors persist

    shamiur
    470f5f9

  29. Part 656: Distinguish quota (3600s) from transient rate-limit (15s) cooldowns

    shamiur
    8801f10

  30. Part 653: Filter pseudo-providers (none/unknown) from health dashboard

    shamiur
    88bf8d0

  31. Part 652: Provider Health Dashboard with 1h/24h stats, P95 latency, error tracking

    shamiur
    3685860

  32. Part 651: Exponential backoff + smart per-provider cooldowns

    shamiur
    3fd1057

2 days ago

  1. Part 650: Make local model log labels dynamic

    shamiur
    43f0321

  2. Part 648: Revert to Qwen2.5-0.5B — SmolLM-135M hallucinates

    shamiur
    b7cd8ae

  3. Part 647: Hardcode SmolLM path in _model_path() to bypass env vars

    shamiur
    5596c7b

  4. Part 646: Force SmolLM path in code to bypass HF secret limits

    shamiur
    9998949

  5. Part 645: Fix SmolLM 404 by using second-state community repo

    shamiur
    adcfbf8

  6. Part 645: Add SmolLM-135M download and preload logic

    shamiur
    c76112c

  7. Part 643: Beautiful formatting for time and search tools

    shamiur
    1d93cd2

  8. Part 642: Hardcode verbose=False to stop C++ log spam

    shamiur
    70751fd

  9. Part 641: Update SambaNova model to Meta-Llama-3.3-70B-Instruct

    shamiur
    6e02718

  10. Part 640: Switch SambaNova to 8B model for better free-tier reliability

    shamiur
    bf62a1b

  11. Part 639: Update Cerebras and SambaNova model IDs to current versions

    shamiur
    9c82c10

  12. Part 638: Add Cerebras, SambaNova, and Together AI as free fast providers

    shamiur
    6545bf5

  13. Part 635: Switch HF provider to Llama-3.3-70B-Instruct for reliable routing

    shamiur
    502726c

  14. Part 634: Add Hugging Face Inference Providers as a fast router

    shamiur
    16d4b0c

  15. Part 632: Hardcode n_ctx=512, restore n_batch=512 for local model speed

    shamiur
    11e6287

  16. Part 630: Optimize local model (n_ctx=512, n_batch=64) + add Test Connection button

    shamiur
    9b72451

  17. Part 629: Bump local timeout to 200s, reduce max_tokens to 32 for speed

    shamiur
    e04d79a

  18. Part 628: Bypass create_chat_completion (hangs) with manual ChatML + create_completion

    shamiur
    4583269